logoalt Hacker News

baobabKoodaa • yesterday at 9:01 PM • 3 replies • view on HN

Everything you said here is false. No, I didn't enter the AI space during the vibe coding era. I was training custom ML models back in 2017. And no, there haven't been models comparable to Jev before Jev was published.

Jev is:

- accurate

- general purpose

- fast and cheap

Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.

Replies

gpugreg • yesterday at 11:02 PM

    > I was training custom ML models back in 2017.
Maybe you are a good person to ask my question then. I have not looked into Jev much, but is it much different from using a regular LLM and constraining its token output to the action space? (e.g. like using llama.cpp's GBNF grammars). Is it just that Jev's "confidence scores" are significantly better than the softmaxed logits? Or is there something else I am missing?
➕ show 1 reply
hbrn • yesterday at 9:19 PM

> Models we had before Jev had at most 2/3 of above qualities, but none of them were 3/3.

You're the one being deceptive here. Jev is trading accuracy, speed, and cost for generality. It's less accurate, slower and more expensive than trained classifiers. So it's still 2 out of 3, but with decimals. Maybe 2.2 out of 3 if I'm being charitable.

And the reason we didn't have that before is because nobody thought it's a good tradeoff.

➕ show 1 reply
prometheus1992 • yesterday at 10:13 PM

>>I was training custom ML models back in 2017

but you truly do sound like an angry 19 year old from your arguments.

- accurate - on what? on trust me bro benchmarks?

- zero-shot model are fundamentally general purpose.

- fast and cheap ; models on hf are FREE and fast enough.

➕ show 1 reply